Get the app
← back to catalog · registered 2026-09-01 09:03

3MPER0RR/Phi-4-mini-3MPER0RR-abliterated

3MPER0RR Phi 3.8B
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/3MPER0RR%2FPhi-4-mini-3MPER0RR-abliterated"
Response includes
  • classification unknown
  • files 10
  • hub_downloads_all_time 1,713
  • author_summary 37 models
  • readme_text full
Try next
GET/models?author=3MPER0RR
All 37 models by 3MPER0RR
 GET/models?family=phi&method=unknown
Sibling phi models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
How we label → About ? →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
2K
922 last 30d - active
Likes
0
Model age
6w ago
created 2026-08-30
Downloads over time
Now1.9K→from11↑17,373%
07041.4K2.1K11 on Sep 11.9K on Oct 17SepOct
Sep 1 → Oct 17 · 47 snapshots · spans 46 days

Metadata

License
mit
Tags
safetensors phi3 text-generation conversational custom_code base_model:microsoft/Phi-4-mini-instruct base_model:finetune:microsoft/Phi-4-mini-instruct license:mit region:us

Related

Other by 3MPER0RR
GLM-4.6V-Flash-3MPER0RR-abliterated 641 TinyLlama-3MPER0RR-abliterated 605 Qwen3-06B-3MPER0RR-abliterated 585 Qwen3-4B-F32-BF16-3MPER0RR-abliterated 513 gpt-oss-20b-3MPER0RR-abliterated 497
Total size
7.15 GB
Files
10
Quantizations
1
Registered
2026-09-01 09:03
Last updated on HF
2026-09-24 23:35
Source huggingface.co/3MPER0RR/Phi-4-mini-3MPER0RR-abliterated ↗

Files by quantization

Auxiliary files 10 files 7.16 GB
model-00001-of-00002.safetensors 4.57 GB a16f9631 download
model-00002-of-00002.safetensors 2.58 GB ca67ef20 download
tokenizer.json 14.8 MB 4fa972fb download
model.safetensors.index.json 15.9 KB 7a1c24de download
config.json 2.51 KB 51744640 download
.gitattributes 1.53 KB 52373fe2 download
README.md 596 B 1b75c822 download
chat_template.jinja 423 B a9c00dd9 download
tokenizer_config.json 350 B a3bf1d4c download
generation_config.json 169 B d5e8692b download

README current version from Hugging Face

license: mit

Microsoft Phi-4-mini 4B — Modified / Obliterated Version

Experimental modified / abliterated version of Microsoft Phi-4-mini 4B.

The model was subjected to an experimental modification process, subsequently tested and saved for research and experimentation purposes.

Model: Microsoft Phi-4-mini 4B
Trials: 40
Status: Tested and saved
Original model: Microsoft

This repository contains a modified model artifact derived from the original release. The original model, authorship and license remain attributed to Microsoft.

Research and experimentation

README history 7 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-24Update README.md62d677d684 B
    Loading...
  2. 2026-09-19Update README.md25d683b670 B
    Loading...
  3. 2026-09-07Update README.mdc3e2766626 B
    Loading...
  4. 2026-09-01Update README.mddd749b6626 B
    Loading...
  5. 2026-09-01Update README.md77afcee596 B
    Loading...
  6. 2026-08-30Update README.md36ceba8596 B
    Loading...
  7. 2026-08-30initial commit364e94321 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration